{"total":25,"rows":[{"id":"2410.07574","title":"Gap-Dependent Bounds for Q-Learning using Reference-Advantage Decomposition","created":"2024-10-10","cited_by_count":8,"area":"deeprl"},{"id":"2406.01386","title":"Combinatorial Multivariant Multi-Armed Bandits with Applications to Episodic Reinforcement Learning and Beyond","created":"2024-06-03","cited_by_count":7,"area":"deeprl"},{"id":"2403.11637","title":"The Value of Reward Lookahead in Reinforcement Learning","created":"2024-03-18","cited_by_count":6,"area":"deeprl"},{"id":"2505.11478","title":"Automatic Reward Shaping from Confounded Offline Data","created":"2025-05-16","cited_by_count":6,"area":"deeprl"},{"id":"2404.10745","title":"Achieving Constant Regret in Linear Markov Decision Processes","created":"2024-04-16","cited_by_count":3,"area":"deeprl"},{"id":"2401.17880","title":"Graph Attention-based Reinforcement Learning for Trajectory Design and Resource Assignment in Multi-UAV Assisted Communication","created":"2024-01-31","cited_by_count":2,"area":"deeprl"},{"id":"2403.00930","title":"Scale-free Adversarial Reinforcement Learning","created":"2024-03-01","cited_by_count":2,"area":"deeprl"},{"id":"2406.07897","title":"When Do Skills Help Reinforcement Learning? A Theoretical Analysis of Temporal Abstractions","created":"2024-06-12","cited_by_count":2,"area":"deeprl"},{"id":"2503.00810","title":"Minimax Optimal Reinforcement Learning with Quasi-Optimism","created":"2025-03-02","cited_by_count":2,"area":"deeprl"},{"id":"2506.04626","title":"Regret-Optimal Q-Learning with Low Cost for Single-Agent and Federated Reinforcement Learning","created":"2025-06-05","cited_by_count":2,"area":"deeprl"},{"id":"2506.24005","title":"Provably Efficient and Agile Randomized Q-Learning","created":"2025-06-30","cited_by_count":2,"area":"deeprl"},{"id":"2507.11706","title":"Reinforcement Learning from Adversarial Preferences in Tabular MDPs","created":"2025-07-15","cited_by_count":2,"area":"deeprl"},{"id":"2405.18793","title":"Policy Zooming: Adaptive Discretization-based Infinite-Horizon Average-Reward Reinforcement Learning","created":"2024-05-29","cited_by_count":1,"area":"deeprl"},{"id":"2411.11647","title":"Near-Optimal Reinforcement Learning with Shuffle Differential Privacy","created":"2024-11-18","cited_by_count":1,"area":"deeprl"},{"id":"2508.02103","title":"Instance-Dependent Continuous-Time Reinforcement Learning via Maximum Likelihood Estimation","created":"2025-08-04","cited_by_count":1,"area":"deeprl"},{"id":"2509.17092","title":"On the Limits of Tabular Hardness Metrics for Deep RL: A Study with the Pharos Benchmark","created":"2025-09-21","cited_by_count":1,"area":"deeprl"},{"id":"2510.06647","title":"Q-Learning with Fine-Grained Gap-Dependent Regret","created":"2025-10-08","cited_by_count":1,"area":"deeprl"},{"id":"2511.18247","title":"Tail Distribution of Regret in Optimistic Reinforcement Learning","created":"2025-11-23","cited_by_count":1,"area":"deeprl"},{"id":"2409.18439","title":"State-free Reinforcement Learning","created":"2024-09-27","cited_by_count":0,"area":"deeprl"},{"id":"2509.02737","title":"Imitate Optimal Policy: Prevail and Induce Action Collapse in Policy Gradient","created":"2025-09-02","cited_by_count":0,"area":"deeprl"},{"id":"2510.19528","title":"Learning Upper Lower Value Envelopes to Shape Online RL: A Principled Approach","created":"2025-10-22","cited_by_count":0,"area":"deeprl"},{"id":"2601.10418","title":"Reinforcement Learning with Multi-Step Lookahead Information Via Adaptive Batching","created":"2026-01-15","cited_by_count":0,"area":"deeprl"},{"id":"2605.15692","title":"Tighter Regret Bounds for Contextual Action-Set Reinforcement Learning","created":"2026-05-15","cited_by_count":0,"area":"deeprl"},{"id":"2608.07725","title":"Finite Constant Frontiers and Auditable Regret Certificates for Average-Reward Reinforcement Learning","created":"2026-08-07","cited_by_count":0,"area":"deeprl"},{"id":"2609.36486","title":"Optimal Multi-Reward Reinforcement Learning","created":"2026-09-29","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}